How to Detect Possible Additional Outliers

Case of Interval Uncertainty

authored by
Hani Dbouk, Steffen Schön, Ingo Neumann, Vladik Kreinovichy
Abstract

In many practical situations, measurements are characterized by interval uncertainty - namely, based on each measurement result, the only information that we have about the actual value of the measured quantity is that this value belongs to some interval. If several such intervals - corresponding to measuring the same quantity - have an empty intersection, this means that at least one of the corresponding measurement results is an outlier, caused by a malfunction of the measuring instrument. From the purely mathematical viewpoint, if the intersection is non-empty, there is no reason to be suspicious. However, from the practical viewpoint, if the intersection is too narrow - i.e., almost empty - then we should also be suspicious, and mark this as an possible additional outlier case. In this paper, we describe a natural way to formalize this idea, and an algorithm for detecting such additional possible outliers.

Organisation(s)
Institute of Geodesy
External Organisation(s)
University of Texas at El Paso
Type
Article
Journal
Reliable Computing
Volume
28
Pages
100-106
No. of pages
7
ISSN
1385-3139
Publication date
06.2021
Publication status
Published
Peer reviewed
Yes
ASJC Scopus subject areas
Software, Computational Mathematics, Applied Mathematics
Electronic version(s)
https://www.cs.utep.edu/vladik/2020/tr20-67b.pdf (Access: Open)
 

Details in the research portal "Research@Leibniz University"